SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.

Home Page:https://github.com/SevaSk/ecoute

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Installation on Linux Ubuntu 22

hubyhuby opened this issue · comments

I am trying to install on Ubuntu linux 22.x,
When installing the requirements , doing
pip install -r requirements.txt

I get this message :
ERROR: Could not find a version that satisfies the requirement PyAudioWPatch==0.2.12.5 (from versions: none)
ERROR: No matching distribution found for PyAudioWPatch==0.2.12.5

image

PS: I am just an end user and don t know python developement.
Just reporting the issue.

Managed to install pyaudio 0.2.13, but is looks like we need a "patch" version 0.2.12.5

sudo apt-get install libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0
sudo apt-get install ffmpeg libav-tools
sudo pip install pyaudio

image

I've managed to launch using PR for Mac... Current version of main repo is not supporting linux because PyAudioWPatch is litterally a "PyAudio Windows Patch" . So in mac repo this is fixed, and something is working on linux. There is another problem still something wrong with default speaker. it's pointing to the wrong device, and correct device has no "source" somehow, so it throws errors. For the moment all this will not work on linux anyway. Unfortunately this is my first encounter with python code, so there is not much i can do. Microphone Input is working by the way, so you can use it as assistant for linux LOL

In the requirements.txt comment the line with PyAudioWPatch and done
then install manually pyaudio